Agentic clinical reasoning over longitudinal myeloma records: a retrospective evaluation against expert consensus

• URL: http://arxiv.org/abs/2604.24473v1
• Date: Mon, 27 Apr 2026 13:41:18 GMT
• Title: Agentic clinical reasoning over longitudinal myeloma records: a retrospective evaluation against expert consensus
• Abstract summary: Multiple myeloma is managed through sequential lines of therapy over years to decades.<n>A retrospective evaluation was conducted on longitudinal clinical records of 811 myeloma patients treated at a tertiary centre (2001-2026)<n>An agentic reasoning system was compared against single-pass retrieval-augmented generation (RAG), iterative RAG, and full-context input on 469 patient-question pairs.<n>Agentic reasoning was the only approach to exceed the shared ceiling, with gains concentrated on the most complex questions and longest records.
• Score: 13.511095666949055
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multiple myeloma is managed through sequential lines of therapy over years to decades, with each decision depending on cumulative disease history distributed across dozens to hundreds of heterogeneous clinical documents. Whether LLM-based systems can synthesise this evidence at a level approaching expert agreement has not been established. A retrospective evaluation was conducted on longitudinal clinical records of 811 myeloma patients treated at a tertiary centre (2001-2026), covering 44,962 documents and 1,334,677 laboratory values, with external validation on MIMIC-IV. An agentic reasoning system was compared against single-pass retrieval-augmented generation (RAG), iterative RAG, and full-context input on 469 patient-question pairs from 48 templates at three complexity levels. Reference labels came from double annotation by four oncologists with senior haematologist adjudication. Iterative RAG and full-context input converged on a shared ceiling (75.4% vs 75.8%, p = 1.00). The agentic system reached 79.6% concordance (95% CI 76.4-82.8), exceeding both baselines (+3.8 and +4.2 pp; p = 0.006 and 0.007). Gains rose with question complexity, reaching +9.4 pp on criteria-based synthesis (p = 0.032), and with record length, reaching +13.5 pp in the top decile (n = 10). The system error rate (12.2%) was comparable to expert disagreement (13.6%), but severity was inverted: 57.8% of system errors were clinically significant versus 18.8% of expert disagreements. Agentic reasoning was the only approach to exceed the shared ceiling, with gains concentrated on the most complex questions and longest records. The greater clinical consequence of residual system errors indicates that prospective evaluation in routine care is required before these findings translate into patient benefit.

Related papers

• Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting [59.709162055944915]
  ThyroidXAgent is an agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence record.<n>It was evaluated on 28,458 non-overlapping test cases, including 8,721 cases from 35 centres in the private NHC-MISD-TUS cohort.<n>It achieved a mean Dice score of 87.21 percent for segmentation and a mean AUROC of 0.9466 for benign-malignant classification.
  arXiv  Detail & Related papers  (2026-08-12T21:02:59Z)
• Characterizing Treatment-Context Medication Evidence Across Clinic Notes and Structured EHR Medication History [1.6612653577971574]
  Clinic notes and structured electronic health record (EHR) medication history often contain different medication information.<n>Same-visit disagreement may result from note-side normalization errors, differences in terminology or timing, or actual differences in documentation.<n>We developed a note-grounded approach that uses large language model (LLM) assisted reference construction, targeted and random human review, deterministic medication normalization, and semantic and temporal comparisons with structured medication history.
  arXiv  Detail & Related papers  (2026-08-03T01:00:01Z)
• ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV [0.0]
  Reasoning benchmarks measure clinical performance on clean inputs.<n>We evaluate the step before reasoning: retrieval over real EHR notes, where negation, temporality, and family-versus-patient attribution can flip a correct answer to a wrong one.<n>EpiKG carries assertion label and a temporality tag with every fact in a patient knowledge graph, then routes retrieval by question intent.
  arXiv  Detail & Related papers  (2026-05-11T18:47:52Z)
• A Breast Vision Pathology Foundation Model for Real-world Clinical Utility [65.57568187389113]
  We present bfBRAVE, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast wholeslide images.<n>BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment.
  arXiv  Detail & Related papers  (2026-05-06T07:44:39Z)
• A Decade-Scale Benchmark Evaluating LLMs' Clinical Practice Guidelines Detection and Adherence in Multi-turn Conversations [60.2076951536797]
  Large Language Models (LLMs) are increasingly deployed in healthcare scenarios.<n>It is unclear to which extend LLMs could identify and adhere to clinical guidelines during conversations.<n>CPGBench is an automated framework benchmarking the clinical guideline detection and adherence capabilities of LLMs.
  arXiv  Detail & Related papers  (2026-03-26T09:00:55Z)
• Agentic Automation of BT-RADS Scoring: End-to-End Multi-Agent System for Standardized Brain Tumor Follow-up Assessment [5.418360208011741]
  The Brain Tumor Reporting and Data System (BT-RADS) standardizes post-treatment MRI response assessment in patients with diffuse gliomas.<n>This study evaluates an end-to-end multi-agent large language model (LLM) and convolutional neural network (CNN) system for automated BT-RADS classification.
  arXiv  Detail & Related papers  (2026-03-23T02:31:54Z)
• Clinician input steers frontier AI models toward both accurate and harmful decisions [10.599240857217811]
  We evaluated 21 large language models (LLMs) across 8 frontier models on differential diagnosis generation and next step recommendations.<n>Expert context significantly improved correct final diagnosis inclusion across all 21 models.<n>In GPT-4o experiments, explicit clinician uncertainty signals improved diagnostic performance after adversarial context.
  arXiv  Detail & Related papers  (2026-03-14T23:47:53Z)
• From Days to Minutes: An Autonomous AI Agent Achieves Reliable Clinical Triage in Remote Patient Monitoring [2.0918370570198763]
  Remote patient monitoring ( RPM) generates vast data, yet landmark trials (Tele-HF, BEAT-HF) failed because data volume overwhelmed clinical staff.<n>We developed Sentinel, an autonomous AI agent using Model Context Protocol (MCP) for contextual triage of RPM vitals.
  arXiv  Detail & Related papers  (2026-03-10T00:50:54Z)
• PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology [48.732366302949515]
  Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safety.<n>We developed a human-in-the-loop pipeline to create expert rubrics for de-identified patient questions.<n>We evaluated 22 proprietary and open-source LLMs using an LLM-as-a-judge framework, measuring clinical completeness, factual accuracy, and web-search integration.
  arXiv  Detail & Related papers  (2026-03-02T00:50:39Z)
• An Agentic System for Rare Disease Diagnosis with Traceable Reasoning [69.46279475491164]
  We introduce DeepRare, the first rare disease diagnosis agentic system powered by a large language model (LLM)<n>DeepRare generates ranked diagnostic hypotheses for rare diseases, each accompanied by a transparent chain of reasoning.<n>The system demonstrates exceptional diagnostic performance among 2,919 diseases, achieving 100% accuracy for 1013 diseases.
  arXiv  Detail & Related papers  (2025-06-25T13:42:26Z)
• MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks [47.486705282473984]
  Large language models (LLMs) achieve near-perfect scores on medical exams.<n>These evaluations inadequately reflect complexity and diversity of real-world clinical practice.<n>We introduce MedHELM, an evaluation framework for assessing LLM performance for medical tasks.
  arXiv  Detail & Related papers  (2025-05-26T22:55:49Z)
• Medical Hallucinations in Foundation Models and Their Impact on Healthcare [71.15392179084428]
  Hallucinations in foundation models arise from autoregressive training objectives.<n>Top-performing models exceeded 97% accuracy when augmented with chain-of-thought prompting.
  arXiv  Detail & Related papers  (2025-02-26T02:30:44Z)
• Clinical prediction system of complications among COVID-19 patients: a development and validation retrospective multicentre study [0.3569980414613667]
  We used data collected from 3,352 COVID-19 patient encounters admitted to 18 facilities between April 1 and April 30, 2020 in Abu Dhabi (AD), UAE. Using data collected during the first 24 hours of admission, the machine learning-based prognostic system predicts the risk of developing any of seven complications during the hospital stay. The system achieves good accuracy across all complications and both regions.
  arXiv  Detail & Related papers  (2020-11-28T18:16:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.